I am Piyush,
a software engineer
based in Bengaluru, India.
About
A proficient software engineer with more than 3 years of experience specializing in Java development. Adept at designing, developing, and maintaining scalable, high-performance applications. Proven ability to collaborate effectively within cross-functional teams to deliver innovative solutions on time. Strong analytical skills, with a knack for diagnosing issues and improving existing code performance. Dedicated to ongoing professional growth and staying current with the latest industry trends and best practices.
Check out my ResumeExpertise
- Software Development
- Data Structures & Algorithms
- Object-Oriented Programming
- Software Architecture & Design
Experience
Oracle
Software Developer 2
September 2024 - Present
Spearheaded efforts for design and development of several product releases, implementing 50+ incremental quality of life improvements and bug fixes, leading to a 40% reduction in customer-reported issues.
Oracle
Software Developer 1
July 2021 - August 2024
Awarded Oracle Pacesetter Award for leading efforts to streamline product functionality and enhance customer experience, resulting in a 30% decrease in customer downtime.
Optum
Intern
June 2020 - July 2020
Completed training in various Machine Learning concepts on Percipio platform as part of the virtual internship process.
Education
NIT Rourkela
B.Tech in Computer Science & Engineering
June 2021
Majored in Computer Science & Engineering. Completed courses in Data Structures and Algorithms, Software Engineering, Data Communication, Operating Systems, Object-Oriented System Design, Database Engineering, Business Research Methodology. Graduated with Honours.
DAV Public School
Matriculation & Intermediate
June 2017
Completed Matriculation with CGPA 10. Completed Intermediate in Science major with 94.2%.
Projects
Here are some of my past projects. Feel free to check them out.
Building Damage Detection Using DWTs and CNNs
Designed a Neural Network model to detect damaged buildings from aerial images using Discrete Wavelet Transforms and Convolutional Neural Networks with high accuracy compared to pretrained models. The images are subjected to DWT to extract features and then CNN is employed to classify the affected areas as damaged or undamaged.
- Discrete Wavelet Transforms
- Convolutional Neural Networks
Automated TSR Using DNN Approach for Intelligent Vehicles
Designed Neural Network models to automate traffic signs recognition for 43 different signs with high accuracy compared to pretrained models. Four variations of deep neural network architectures (FFNN, RBN, CNN, RNN) were designed, tuned and evaluated to select the best performing model.
- Deep Neural Networks
- Image Recognition
Get In Touch
I would love to hear from you. Whether you have a question or just want to chat — shoot me a message.